{"id":"https://openalex.org/W4321366759","doi":"https://doi.org/10.1109/lra.2023.3246844","title":"Overcoming Exploration: Deep Reinforcement Learning for Continuous Control in Cluttered Environments From Temporal Logic Specifications","display_name":"Overcoming Exploration: Deep Reinforcement Learning for Continuous Control in Cluttered Environments From Temporal Logic Specifications","publication_year":2023,"publication_date":"2023-02-20","ids":{"openalex":"https://openalex.org/W4321366759","doi":"https://doi.org/10.1109/lra.2023.3246844"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2023.3246844","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2023.3246844","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766","2377-3774"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001420415","display_name":"Mingyu Cai","orcid":"https://orcid.org/0000-0002-2967-2703"},"institutions":[{"id":"https://openalex.org/I186143895","display_name":"Lehigh University","ror":"https://ror.org/012afjb06","country_code":"US","type":"education","lineage":["https://openalex.org/I186143895"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mingyu Cai","raw_affiliation_strings":["Mechanical Engineering, Lehigh University, Bethlehem, PA, USA"],"raw_orcid":"https://orcid.org/0000-0002-2967-2703","affiliations":[{"raw_affiliation_string":"Mechanical Engineering, Lehigh University, Bethlehem, PA, USA","institution_ids":["https://openalex.org/I186143895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042146883","display_name":"Erfan Aasi","orcid":null},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Erfan Aasi","raw_affiliation_strings":["Mechanical Engineering Department, Boston University, Boston, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mechanical Engineering Department, Boston University, Boston, MA, USA","institution_ids":["https://openalex.org/I111088046"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086742095","display_name":"C\u0103lin Belta","orcid":"https://orcid.org/0000-0002-7141-2657"},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Calin Belta","raw_affiliation_strings":["Mechanical Engineering Department, Boston University, Boston, MA, USA"],"raw_orcid":"https://orcid.org/0000-0002-7141-2657","affiliations":[{"raw_affiliation_string":"Mechanical Engineering Department, Boston University, Boston, MA, USA","institution_ids":["https://openalex.org/I111088046"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086654963","display_name":"Cristian-Ioan Vasile","orcid":"https://orcid.org/0000-0002-1132-1462"},"institutions":[{"id":"https://openalex.org/I186143895","display_name":"Lehigh University","ror":"https://ror.org/012afjb06","country_code":"US","type":"education","lineage":["https://openalex.org/I186143895"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cristian-Ioan Vasile","raw_affiliation_strings":["Mechanical Engineering, Lehigh University, Bethlehem, PA, USA"],"raw_orcid":"https://orcid.org/0000-0002-1132-1462","affiliations":[{"raw_affiliation_string":"Mechanical Engineering, Lehigh University, Bethlehem, PA, USA","institution_ids":["https://openalex.org/I186143895"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.7335,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.91681876,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"8","issue":"4","first_page":"2158","last_page":"2165"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10142","display_name":"Formal Methods in Verification","score":0.9922999739646912,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8307343125343323},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6844069957733154},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6477673053741455},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6294403076171875},{"id":"https://openalex.org/keywords/temporal-logic","display_name":"Temporal logic","score":0.6129356622695923},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5927271246910095},{"id":"https://openalex.org/keywords/linear-temporal-logic","display_name":"Linear temporal logic","score":0.5841798782348633},{"id":"https://openalex.org/keywords/motion-planning","display_name":"Motion planning","score":0.48852550983428955},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.45316919684410095},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.44515734910964966},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4361620843410492},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4189959168434143},{"id":"https://openalex.org/keywords/collision-avoidance","display_name":"Collision avoidance","score":0.41270604729652405},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.4102208912372589},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.18074390292167664},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.10087704658508301},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.07428115606307983}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8307343125343323},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6844069957733154},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6477673053741455},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6294403076171875},{"id":"https://openalex.org/C25016198","wikidata":"https://www.wikidata.org/wiki/Q781833","display_name":"Temporal logic","level":2,"score":0.6129356622695923},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5927271246910095},{"id":"https://openalex.org/C4777664","wikidata":"https://www.wikidata.org/wiki/Q1536492","display_name":"Linear temporal logic","level":2,"score":0.5841798782348633},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.48852550983428955},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.45316919684410095},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.44515734910964966},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4361620843410492},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4189959168434143},{"id":"https://openalex.org/C2780864053","wikidata":"https://www.wikidata.org/wiki/Q5147495","display_name":"Collision avoidance","level":3,"score":0.41270604729652405},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.4102208912372589},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.18074390292167664},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.10087704658508301},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.07428115606307983},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C121704057","wikidata":"https://www.wikidata.org/wiki/Q352070","display_name":"Collision","level":2,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2023.3246844","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2023.3246844","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766","2377-3774"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309565","display_name":"Boston University","ror":"https://ror.org/05qwgg493"},{"id":"https://openalex.org/F4320310365","display_name":"Lehigh University","ror":"https://ror.org/012afjb06"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1498432697","https://openalex.org/W1971086298","https://openalex.org/W2000359213","https://openalex.org/W2089003125","https://openalex.org/W2134673975","https://openalex.org/W2145339207","https://openalex.org/W2150335178","https://openalex.org/W2336416123","https://openalex.org/W2487186542","https://openalex.org/W2736601468","https://openalex.org/W2741122588","https://openalex.org/W2788862220","https://openalex.org/W2963099939","https://openalex.org/W2963821308","https://openalex.org/W2963864421","https://openalex.org/W2964337106","https://openalex.org/W2972500268","https://openalex.org/W2995074243","https://openalex.org/W3021964239","https://openalex.org/W3033621224","https://openalex.org/W3080598349","https://openalex.org/W3092156990","https://openalex.org/W3097945779","https://openalex.org/W3130777366","https://openalex.org/W3136316167","https://openalex.org/W3198607174","https://openalex.org/W4205451316","https://openalex.org/W4214717370","https://openalex.org/W4246226690","https://openalex.org/W4321366759","https://openalex.org/W6638018090","https://openalex.org/W6655221434","https://openalex.org/W6684921986","https://openalex.org/W6738796088","https://openalex.org/W6741002519","https://openalex.org/W6742461812","https://openalex.org/W6747473740","https://openalex.org/W6752298494","https://openalex.org/W6757469721","https://openalex.org/W6790722625","https://openalex.org/W6800661141","https://openalex.org/W6801468180"],"related_works":["https://openalex.org/W4381746183","https://openalex.org/W2124110813","https://openalex.org/W3021103820","https://openalex.org/W2763487042","https://openalex.org/W2031188261","https://openalex.org/W4232446061","https://openalex.org/W4285022830","https://openalex.org/W2020883449","https://openalex.org/W3035590440","https://openalex.org/W3205267199"],"abstract_inverted_index":{"Model-free":[0],"continuous":[1],"control":[2],"for":[3,17,76],"robot":[4,79],"navigation":[5],"tasks":[6,61,138],"using":[7,64],"Deep":[8],"Reinforcement":[9],"Learning":[10],"(DRL)":[11],"that":[12,139],"relies":[13],"on":[14],"noisy":[15],"policies":[16],"exploration":[18,49,106,157],"is":[19,45,91,148],"sensitive":[20],"to":[21,121,150],"the":[22,89,102,133],"density":[23],"of":[24,105,158],"rewards.":[25],"In":[26],"practice,":[27],"robots":[28,159],"are":[29,62,140],"usually":[30],"deployed":[31],"in":[32,48,84,142,164],"cluttered":[33,86,166],"environments,":[34],"containing":[35],"many":[36],"obstacles":[37],"and":[38,156],"narrow":[39],"passageways.":[40],"Designing":[41],"dense":[42],"effective":[43],"rewards":[44],"challenging,":[46],"resulting":[47],"issues":[50],"during":[51,107],"training.":[52],"Such":[53],"a":[54,71,78,85,94,111,143],"problem":[55],"becomes":[56],"even":[57],"more":[58],"serious":[59],"when":[60,88],"described":[63],"temporal":[65],"logic":[66],"specifications.":[67],"This":[68],"work":[69],"presents":[70],"deep":[72],"policy":[73],"gradient":[74],"algorithm":[75],"controlling":[77],"with":[80,161],"unknown":[81],"dynamics":[82],"operating":[83],"environment":[87],"task":[90],"specified":[92],"as":[93],"Linear":[95],"Temporal":[96],"Logic":[97],"(LTL)":[98],"formula.":[99],"To":[100,126],"overcome":[101],"environmental":[103],"challenge":[104],"training,":[108],"we":[109],"propose":[110],"novel":[112],"path":[113],"planning-guided":[114],"reward":[115],"scheme":[116],"by":[117],"integrating":[118],"sampling-based":[119],"methods":[120],"effectively":[122],"complete":[123],"goal-reaching":[124],"missions.":[125],"facilitate":[127],"LTL":[128,134],"satisfaction,":[129],"our":[130],"approach":[131],"decomposes":[132],"mission":[135],"into":[136],"sub-goal-reaching":[137],"solved":[141],"distributed":[144],"manner.":[145],"Our":[146],"framework":[147],"shown":[149],"significantly":[151],"improve":[152],"performance":[153],"(effectiveness,":[154],"efficiency)":[155],"tasked":[160],"complex":[162],"missions":[163],"large-scale":[165],"environments.":[167]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":12}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}